echarlaix HF staff commited on
Commit
69e7b04
1 Parent(s): fea302f

update loading instructions

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -47,10 +47,10 @@ The original fp32 model comes from the fine-tuned model [bart-large-mrpc](https:
47
  #### Load with optimum:
48
 
49
  ```python
50
- from optimum.intel.neural_compressor.quantization import IncQuantizedModelForSequenceClassification
51
- int8_model = IncQuantizedModelForSequenceClassification.from_pretrained(
52
- 'Intel/bart-large-mrpc-int8-dynamic',
53
- )
54
  ```
55
 
56
  ### ONNX
@@ -72,4 +72,4 @@ The original fp32 model comes from the fine-tuned model [bart-large-mrpc](https:
72
  ```python
73
  from optimum.onnxruntime import ORTModelForSequenceClassification
74
  model = ORTModelForSequenceClassification.from_pretrained('Intel/bart-large-mrpc-int8-dynamic')
75
- ```
 
47
  #### Load with optimum:
48
 
49
  ```python
50
+ from optimum.intel import INCModelForSequenceClassification
51
+
52
+ model_id = "Intel/bart-large-mrpc-int8-dynamic"
53
+ int8_model = INCModelForSequenceClassification.from_pretrained(model_id)
54
  ```
55
 
56
  ### ONNX
 
72
  ```python
73
  from optimum.onnxruntime import ORTModelForSequenceClassification
74
  model = ORTModelForSequenceClassification.from_pretrained('Intel/bart-large-mrpc-int8-dynamic')
75
+ ```